Sampling procedures in selection and allocation of participants

Sampling procedures

The method of sampling utilised can be used to minimise extraneous variables. A sampling method is often chosen depending on what the extraneous variables which are being minimised are. Sampling procedures include convenience sampling, random sampling, stratified sampling, and random stratified sampling.

Convenience sampling

Convenience sampling involves selection merely by what is quick and easy. It makes no attempt for the sample to be representative of the population, and is often biased. Whilst convenience sampling is easy (an experimenter may take, for example, one whole class out of a school of 1000 students), results cannot be generalised. Convenience sampling comes with many possible extraneous and confounding variables.

Random sampling

In random sampling, each member of a population has an equal chance of being part of the sample. Extraneous variables are likely to be minimised, assuming that the sample is large enough.

Stratified sampling

When a particular characteristic is important to a study, stratified sampling may be used. Stratified sampling may eliminate extraneous variables regarding a particular characteristic. Using this sampling method, the proportion of participants with a particular characteristic (red hair, for example) is the same as the proportion of participants with that same characteristic in the wider population.

Random stratified sampling

Random stratified sampling is a more elaborate method of stratified sampling. Each member of a population with a particular characteristic (red hair, for example) has an equal chance of being selected to be part of the sample. As a result, the sample will consist of proportionate sizes of participants with particular characteristics to the wider population. Random stratified sampling is the most accurate sampling method, which means that it is likely to best minimise extraneous variables, but it is also the most time-consuming.

Allocation of participants

There are usually two groups or conditions: the experimental group/condition and the control group/condition.

Control group

The control group is exposed to the control condition, whereby the independent variable is either absent or neutral. The results of this group provide a benchmark or baseline standard to which other results, and therefore the impact of the independent variable, can be compared.

For example, to test the hypothesis that taking a specific type of medication makes you run faster, the control group would not be exposed to the medication.

Experimental group

The experimental group is exposed to the experimental condition, whereby the independent variable is present. The results of this group are used to measure the impact of the independent variable by comparison to the results of the control group, whereby the independent variable is either neutral or absent.

For example, to test the hypothesis that taking a specific type of medication makes you run faster, the experimental group would be exposed to the medication.